Model techniques map
Techniquesinference & servinginference quantization

general family · filed under inference & serving

Large-model compression using quantization and speculative sampling

The evidence groups quantization, low-bit quantization, and speculative sampling as compression tools without identifying a single combined method.

source
1
model
1
lab adopt it
1
strongest
optional

How sources treat it

One count per evidence span, weakest treatment to strongest.

optional 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

AngelSlim supports a comprehensive suite of compression tools for large-scale multimodal models, including common quantization algorithms, low-bit quantization, and speculative sampling

optionalinference servingin AngelSlimTencent

Filed alongside

Other methods under inference & serving :: inference quantization.